# Research Papers — 2025-12 · bundle page 6 of 175 > Full-text markdown of papers #251–300 of 8703 published in 2025-12, newest first. AI-readable mirrors of the full 8703-paper 2025-12 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2025-12/page/6 [← Previous bundle](https://aipod.dev/papers/archive/2025-12/page/5.md) [Next bundle →](https://aipod.dev/papers/archive/2025-12/page/7.md) ### Localized Calibrated Uncertainty in Code Language Models Authors: David Gros, Prem Devanbu Published: 2025-12-31 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2512.24560v1 Large Language models (LLMs) can generate complicated source code from natural language prompts. However, LLMs can generate output that deviates from what the user wants, requiring supervision and editing. To support this process, we offer techniques to localize where generations might be misaligned from user intent. We first create a dataset of "Minimal Intent Aligning Patches" of repaired LLM generated programs. Each program uses test cases to verify correctness. After creating a dataset of programs, we measure how well various techniques can assign a well-calibrated probability to indicate which parts of code will be edited in a minimal patch (i.e., give a probability that corresponds with empirical odds it is edited). We compare white-box probing (where we propose a technique for efficient arbitrary-span querying), against black-box reflective and self-consistency based approaches. We find probes with a small supervisor model can achieve low calibration error and Brier Skill Score of approx 0.2 estimating edited lines on code generated by models many orders of magnitude larger. We discuss the generalizability of the techniques, and the connections to AI oversight and control, finding a probe trained only on code shows some signs of generalizing to natural language errors if new probability scaling is allowed. --- ### Evolutionary Discovery of Sequence Acceleration Methods for Slab Geometry Neutron Transport Authors: Japan K. Patel, Barry D. Ganapol, Anthony Magliari, Matthew C. Schmidt, Todd A. Wareing Published: 2025-12-31 Categories: cs.NE arXiv: https://arxiv.org/abs/2512.24559v1 We present a genetic programming approach to automatically discover convergence acceleration methods for discrete ordinates solutions of neutron transport problems in slab geometry. Classical acceleration methods such as Aitken's delta-squared and Wynn epsilon assume specific convergence patterns and do not generalize well to the broad set of transport problems encountered in practice. We evolved mathematical formulas specifically tailored to SN convergence characteristics in this work. The discovered accelerator, featuring second differences and cross-product terms, achieved over 75 percent success rate in improving convergence compared to raw sequences - almost double that observed for classical techniques for the problem set considered. This work demonstrates the potential for discovering novel numerical methods in computational physics via genetic programming and attempts to honor Prof. Ganapol's legacy of advancing experimental mathematics applied to neutron transport. --- ### Probabilistic Computers for Neural Quantum States Authors: Shuvro Chowdhury, Jasper Pieterse, Navid Anjum Aadit, Shaila Niazi, Johan H. Mentink, Kerem Y. Camsari Published: 2025-12-31 Categories: quant-ph, cond-mat.dis-nn, cs.ET, cs.LG arXiv: https://arxiv.org/abs/2512.24558v2 Neural quantum states efficiently represent many-body wavefunctions with neural networks, but the cost of Monte Carlo sampling limits their scaling to large system sizes. Here we address this challenge by combining sparse Boltzmann machine architectures with probabilistic computing hardware. We implement a probabilistic computer on field-programmable gate arrays (FPGAs) and use it as a fast sampler for energy-based neural quantum states. For the two-dimensional transverse-field Ising model at criticality, we obtain accurate ground-state energies for lattices up to 80$\times$80 (6400 spins) using a custom multi-FPGA cluster. Furthermore, we introduce a dual-sampling algorithm to train deep Boltzmann machines, replacing intractable marginalization with conditional sampling over auxiliary layers. This enables the training of sparse deep models and improves parameter efficiency relative to shallow networks. We further implement this algorithm on a single FPGA, demonstrating the training of deep Boltzmann machines for systems as large as $30 \times 30$ (900 spins). Together, these results demonstrate that probabilistic hardware can overcome the sampling bottleneck in variational simulation of quantum many-body systems, opening a path to larger system sizes and deeper variational architectures. --- ### Probabilistic Computers for Neural Quantum States Authors: Shuvro Chowdhury, Jasper Pieterse, Navid Anjum Aadit, Johan H. Mentink, Kerem Y. Camsari Published: 2025-12-31 Categories: quant-ph, cond-mat.dis-nn, cs.ET, cs.LG arXiv: https://arxiv.org/abs/2512.24558v1 Neural quantum states efficiently represent many-body wavefunctions with neural networks, but the cost of Monte Carlo sampling limits their scaling to large system sizes. Here we address this challenge by combining sparse Boltzmann machine architectures with probabilistic computing hardware. We implement a probabilistic computer on field programmable gate arrays (FPGAs) and use it as a fast sampler for energy-based neural quantum states. For the two-dimensional transverse-field Ising model at criticality, we obtain accurate ground-state energies for lattices up to 80 $\times$ 80 (6400 spins) using a custom multi-FPGA cluster. Furthermore, we introduce a dual-sampling algorithm to train deep Boltzmann machines, replacing intractable marginalization with conditional sampling over auxiliary layers. This enables the training of sparse deep models and improves parameter efficiency relative to shallow networks. Using this algorithm, we train deep Boltzmann machines for a system with 35 $\times$ 35 (1225 spins). Together, these results demonstrate that probabilistic hardware can overcome the sampling bottleneck in variational simulation of quantum many-body systems, opening a path to larger system sizes and deeper variational architectures. --- ### Safe in the Future, Dangerous in the Past: Dissecting Temporal and Linguistic Vulnerabilities in LLMs Authors: Muhammad Abdullahi Said, Muhammad Sammani Sani Published: 2025-12-31 Categories: cs.CL, cs.AI, cs.CY arXiv: https://arxiv.org/abs/2512.24556v2 As Large Language Models (LLMs) integrate into critical global infrastructure, the assumption that safety alignment transfers zero-shot from English to other languages remains a dangerous blind spot. This study presents a systematic audit of three state of the art models (GPT-5.1, Gemini 3 Pro, and Claude 4.5 Opus) using HausaSafety, a novel adversarial dataset grounded in West African threat scenarios (e.g., Yahoo-Yahoo fraud, Dane gun manufacturing). Employing a 2 x 4 factorial design across 1,440 evaluations, we tested the non-linear interaction between language (English vs. Hausa) and temporal framing. Our results challenge the narrative of the multilingual safety gap. Instead of a simple degradation in low-resource settings, we identified a complex interference mechanism in which safety is determined by the intersection of variables. Although the models exhibited a reverse linguistic vulnerability with Claude 4.5 Opus proving significantly safer in Hausa (45.0%) than in English (36.7%) due to uncertainty-driven refusal, they suffered catastrophic failures in temporal reasoning. We report a profound Temporal Asymmetry, where past-tense framing bypassed defenses (15.6% safe) while future-tense scenarios triggered hyper-conservative refusals (57.2% safe). The magnitude of this volatility is illustrated by a 9.2x disparity between the safest and most vulnerable configurations, proving that safety is not a fixed property but a context-dependent state. We conclude that current models rely on superficial heuristics rather than robust semantic understanding, creating Safety Pockets that leave Global South users exposed to localized harms. We propose Invariant Alignment as a necessary paradigm shift to ensure safety stability across linguistic and temporal shifts. --- ### Safe in the Future, Dangerous in the Past: Dissecting Temporal and Linguistic Vulnerabilities in LLMs Authors: Muhammad Abdullahi Said, Muhammad Sammani Sani Published: 2025-12-31 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.24556v1 As Large Language Models (LLMs) integrate into critical global infrastructure, the assumption that safety alignment transfers zero-shot from English to other languages remains a dangerous blind spot. This study presents a systematic audit of three state of the art models (GPT-5.1, Gemini 3 Pro, and Claude 4.5 Opus) using HausaSafety, a novel adversarial dataset grounded in West African threat scenarios (e.g., Yahoo-Yahoo fraud, Dane gun manufacturing). Employing a 2 x 4 factorial design across 1,440 evaluations, we tested the non-linear interaction between language (English vs. Hausa) and temporal framing. Our results challenge the prevailing multilingual safety gap narrative. Instead of a simple degradation in low-resource settings, we identified a mechanism of Complex Interference where safety is determined by the intersection of variables. While models exhibited a Reverse Linguistic with Claude 4.5 Opus proving significantly safer in Hausa (45.0%) than in English (36.7%) due to uncertainty-driven refusal they suffered catastrophic failures in temporal reasoning. We report a profound Temporal Asymmetry, where past-tense framing bypassed defenses (15.6% safe) while future-tense scenarios triggered hyper-conservative refusals (57.2% safe). The magnitude of this volatility is illustrated by a 9.2x disparity between the safest and most vulnerable configurations, proving that safety is not a fixed property but a context-dependent state. We conclude that current models rely on superficial heuristics rather than robust semantic understanding, creating Safety Pockets that leave Global South users exposed to localized harms. We propose Invariant Alignment as a necessary paradigm shift to ensure safety stability across linguistic and temporal shifts. --- ### From Perception to Punchline: Empowering VLM with the Art of In-the-wild Meme Authors: Xueyan Li, Yingyi Xue, Mengjie Jiang, Qingzi Zhu, Yazhe Niu Published: 2025-12-31 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.24555v2 Generating humorous memes is a challenging multimodal task that moves beyond direct image-to-caption supervision. It requires a nuanced reasoning over visual content, contextual cues, and subjective humor. To bridge this gap between visual perception and humorous punchline creation, we propose HUMOR}, a novel framework that guides VLMs through hierarchical reasoning and aligns them with group-wise human preferences. First, HUMOR employs a hierarchical, multi-path Chain-of-Thought (CoT): the model begins by identifying a template-level intent, then explores diverse reasoning paths under different contexts, and finally anchors onto a high-quality, context-specific path. This CoT supervision, which traces back from ground-truth captions, enhances reasoning diversity. We further analyze that this multi-path exploration with anchoring maintains a high expected humor quality, under the practical condition that high-quality paths retain significant probability mass. Second, to capture subjective humor, we train a pairwise reward model that operates within groups of memes sharing the same template. Following established theory, this approach ensures a consistent and robust proxy for human preference, even with subjective and noisy labels. The reward model then enables a group-wise reinforcement learning optimization, guaranteeing providing a theoretical guarantee for monotonic improvement within the trust region. Extensive experiments show that HUMOR empowers various VLMs with superior reasoning diversity, more reliable preference alignment, and higher overall meme quality. Beyond memes, our work presents a general training paradigm for open-ended, human-aligned multimodal generation, where success is guided by comparative judgment within coherent output group. --- ### From Perception to Punchline: Empowering VLM with the Art of In-the-wild Meme Authors: Xueyan Li, Yingyi Xue, Mengjie Jiang, Qingzi Zhu, Yazhe Niu Published: 2025-12-31 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.24555v1 Generating humorous memes is a challenging multimodal task that moves beyond direct image-to-caption supervision. It requires a nuanced reasoning over visual content, contextual cues, and subjective humor. To bridge this gap between visual perception and humorous punchline creation, we propose HUMOR}, a novel framework that guides VLMs through hierarchical reasoning and aligns them with group-wise human preferences. First, HUMOR employs a hierarchical, multi-path Chain-of-Thought (CoT): the model begins by identifying a template-level intent, then explores diverse reasoning paths under different contexts, and finally anchors onto a high-quality, context-specific path. This CoT supervision, which traces back from ground-truth captions, enhances reasoning diversity. We further analyze that this multi-path exploration with anchoring maintains a high expected humor quality, under the practical condition that high-quality paths retain significant probability mass. Second, to capture subjective humor, we train a pairwise reward model that operates within groups of memes sharing the same template. Following established theory, this approach ensures a consistent and robust proxy for human preference, even with subjective and noisy labels. The reward model then enables a group-wise reinforcement learning optimization, guaranteeing providing a theoretical guarantee for monotonic improvement within the trust region. Extensive experiments show that HUMOR empowers various VLMs with superior reasoning diversity, more reliable preference alignment, and higher overall meme quality. Beyond memes, our work presents a general training paradigm for open-ended, human-aligned multimodal generation, where success is guided by comparative judgment within coherent output group. --- ### OCP-GN: A Scalable Second-order Optimizer for Stochastic Optimization Authors: Jindi Zhong, Congyaohui Yin, Zhaorong Zhang, Huanshui Zhang Published: 2025-12-31 Categories: cs.CV, math.OC arXiv: https://arxiv.org/abs/2512.24552v2 This paper proposes a novel second-order optimization algorithm based on the Optimal Control Principle (OCP), applicable to large-scale optimization problems in neural network training. The algorithm has a computational complexity of O(d) and strong robustness. Extensive experiments on multiple benchmarks demonstrate the significant superiority of the proposed method. --- ### OCP-LS: An Efficient Algorithm for Visual Localization Authors: Jindi Zhong, Hongxia Wang, Huanshui Zhang Published: 2025-12-31 Categories: cs.CV, math.OC arXiv: https://arxiv.org/abs/2512.24552v1 This paper proposes a novel second-order optimization algorithm. It aims to address large-scale optimization problems in deep learning because it incorporates the OCP method and appropriately approximating the diagonal elements of the Hessian matrix. Extensive experiments on multiple standard visual localization benchmarks demonstrate the significant superiority of the proposed method. Compared with conventional optimiza tion algorithms, our framework achieves competitive localization accuracy while exhibiting faster convergence, enhanced training stability, and improved robustness to noise interference. --- ### PhyGDPO: Physics-Aware Groupwise Direct Preference Optimization for Physically Consistent Text-to-Video Generation Authors: Yuanhao Cai, Kunpeng Li, Menglin Jia, Jialiang Wang, Junzhe Sun, Feng Liang, Weifeng Chen, Felix Juefei-Xu, Chu Wang, Ali Thabet, Xiaoliang Dai, Xuan Ju et al. Published: 2025-12-31 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.24551v4 Recent advances in text-to-video (T2V) generation have achieved good visual quality, yet synthesizing videos that faithfully follow physical laws remains an open challenge. Existing methods mainly based on graphics or prompt extension struggle to generalize beyond simple simulated environments or learn implicit physical reasoning. The scarcity of training data with rich physics interactions and phenomena is also a problem. In this paper, we first introduce a Physics-Augmented video data construction Pipeline, PhyAugPipe, that leverages a vision-language model (VLM) with chain-of-thought reasoning to collect a large-scale training dataset, PhyVidGen-135K. Then we formulate a principled Physics-aware Groupwise Direct Preference Optimization, PhyGDPO, framework that uses real-world video as winning case to guarantee correct physics learning and builds upon the groupwise Plackett-Luce probabilistic model to capture holistic preferences beyond pairwise comparisons. In PhyGDPO, we design a Physics-Guided Rewarding (PGR) scheme that leverages VLM-based physical rewards to direct the optimization to focus on challenging physics cases. In addition, we propose a LoRA-Switch Reference (LoRA-SR) scheme that avoids full-model duplication as reference for efficient DPO training. Experiments show that our method significantly outperforms state-of-the-art open-source methods on PhyGenBench and VideoPhy2. Please check our project page at https://caiyuanhao1998.github.io/project/PhyGDPO for more video results. Our code, data, and models are publicly available at https://github.com/caiyuanhao1998/Open-PhyGDPO --- ### PhyGDPO: Physics-Aware Groupwise Direct Preference Optimization for Physically Consistent Text-to-Video Generation Authors: Yuanhao Cai, Kunpeng Li, Menglin Jia, Jialiang Wang, Junzhe Sun, Feng Liang, Weifeng Chen, Felix Juefei-Xu, Chu Wang, Ali Thabet, Xiaoliang Dai, Xuan Ju et al. Published: 2025-12-31 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.24551v1 Recent advances in text-to-video (T2V) generation have achieved good visual quality, yet synthesizing videos that faithfully follow physical laws remains an open challenge. Existing methods mainly based on graphics or prompt extension struggle to generalize beyond simple simulated environments or learn implicit physical reasoning. The scarcity of training data with rich physics interactions and phenomena is also a problem. In this paper, we first introduce a Physics-Augmented video data construction Pipeline, PhyAugPipe, that leverages a vision-language model (VLM) with chain-of-thought reasoning to collect a large-scale training dataset, PhyVidGen-135K. Then we formulate a principled Physics-aware Groupwise Direct Preference Optimization, PhyGDPO, framework that builds upon the groupwise Plackett-Luce probabilistic model to capture holistic preferences beyond pairwise comparisons. In PhyGDPO, we design a Physics-Guided Rewarding (PGR) scheme that embeds VLM-based physics rewards to steer optimization toward physical consistency. We also propose a LoRA-Switch Reference (LoRA-SR) scheme that eliminates memory-heavy reference duplication for efficient training. Experiments show that our method significantly outperforms state-of-the-art open-source methods on PhyGenBench and VideoPhy2. Please check our project page at https://caiyuanhao1998.github.io/project/PhyGDPO for more video results. Our code, models, and data will be released at https://github.com/caiyuanhao1998/Open-PhyGDPO --- ### Hierarchical Vector-Quantized Latents for Perceptual Low-Resolution Video Compression Authors: Manikanta Kotthapalli, Banafsheh Rekabdar Published: 2025-12-31 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.24547v1 The exponential growth of video traffic has placed increasing demands on bandwidth and storage infrastructure, particularly for content delivery networks (CDNs) and edge devices. While traditional video codecs like H.264 and HEVC achieve high compression ratios, they are designed primarily for pixel-domain reconstruction and lack native support for machine learning-centric latent representations, limiting their integration into deep learning pipelines. In this work, we present a Multi-Scale Vector Quantized Variational Autoencoder (MS-VQ-VAE) designed to generate compact, high-fidelity latent representations of low-resolution video, suitable for efficient storage, transmission, and client-side decoding. Our architecture extends the VQ-VAE-2 framework to a spatiotemporal setting, introducing a two-level hierarchical latent structure built with 3D residual convolutions. The model is lightweight (approximately 18.5M parameters) and optimized for 64x64 resolution video clips, making it appropriate for deployment on edge devices with constrained compute and memory resources. To improve perceptual reconstruction quality, we incorporate a perceptual loss derived from a pre-trained VGG16 network. Trained on the UCF101 dataset using 2-second video clips (32 frames at 16 FPS), on the test set we achieve 25.96 dB PSNR and 0.8375 SSIM. On validation, our model improves over the single-scale baseline by 1.41 dB PSNR and 0.0248 SSIM. The proposed framework is well-suited for scalable video compression in bandwidth-sensitive scenarios, including real-time streaming, mobile video analytics, and CDN-level storage optimization. --- ### More Than Bits: Multi-Envelope Double Binary Factorization for Extreme Quantization Authors: Yuma Ichikawa, Yoshihiko Fujisawa, Yudai Fujimoto, Akira Sakai, Katsuki Fujisawa Published: 2025-12-31 Categories: cs.LG, cs.AI, cs.CL, stat.ML arXiv: https://arxiv.org/abs/2512.24545v1 For extreme low-bit quantization of large language models (LLMs), Double Binary Factorization (DBF) is attractive as it enables efficient inference without sacrificing accuracy. However, the scaling parameters of DBF are too restrictive; after factoring out signs, all rank components share the same magnitude profile, resulting in performance saturation. We propose Multi-envelope DBF (MDBF), which retains a shared pair of 1-bit sign bases but replaces the single envelope with a rank-$l$ envelope. By sharing sign matrices among envelope components, MDBF effectively maintains a binary carrier and utilizes the limited memory budget for magnitude expressiveness. We also introduce a closed-form initialization and an alternating refinement method to optimize MDBF. Across the LLaMA and Qwen families, MDBF enhances perplexity and zero-shot accuracy over previous binary formats at matched bits per weight while preserving the same deployment-friendly inference primitive. --- ### A Graph Neural Network with Auxiliary Task Learning for Missing PMU Data Reconstruction Authors: Bo Li, Zijun Chen, Haiwang Zhong, Di Cao, Guangchun Ruan Published: 2025-12-31 Categories: eess.SY, cs.LG arXiv: https://arxiv.org/abs/2512.24542v1 In wide-area measurement systems (WAMS), phasor measurement unit (PMU) measurement is prone to data missingness due to hardware failures, communication delays, and cyber-attacks. Existing data-driven methods are limited by inadaptability to concept drift in power systems, poor robustness under high missing rates, and reliance on the unrealistic assumption of full system observability. Thus, this paper proposes an auxiliary task learning (ATL) method for reconstructing missing PMU data. First, a K-hop graph neural network (GNN) is proposed to enable direct learning on the subgraph consisting of PMU nodes, overcoming the limitation of the incompletely observable system. Then, an auxiliary learning framework consisting of two complementary graph networks is designed for accurate reconstruction: a spatial-temporal GNN extracts spatial-temporal dependencies from PMU data to reconstruct missing values, and another auxiliary GNN utilizes the low-rank property of PMU data to achieve unsupervised online learning. In this way, the low-rank properties of the PMU data are dynamically leveraged across the architecture to ensure robustness and self-adaptation. Numerical results demonstrate the superior offline and online performance of the proposed method under high missing rates and incomplete observability. --- ### From Building Blocks to Planning: Multi-Step Spatial Reasoning in LLMs with Reinforcement Learning Authors: Amir Tahmasbi, Sadegh Majidi, Kazem Taram, Aniket Bera Published: 2025-12-31 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2512.24532v1 Spatial reasoning in large language models (LLMs) has gained increasing attention due to applications in navigation and planning. Despite strong general language capabilities, LLMs still struggle with spatial transformations and multi-step planning in structured environments. We propose a two-stage approach that decomposes spatial reasoning into atomic building blocks and their composition. First, we apply supervised fine-tuning on elementary spatial transformations, such as rotation, translation, and scaling, to equip the model with basic spatial physics. We then freeze this physics-aware model and train lightweight LoRA adapters within the GRPO framework to learn policies that compose these building blocks for multi-step planning in puzzle-based environments, in a closed-loop manner. To support this pipeline, we synthesize an ASCII-art dataset and construct a corresponding ASCII-based reinforcement learning environment. Our method consistently outperforms baselines, including the generic backbone, physics-aware model, and end-to-end RL models, under both Dynamic environments with explicit state updates and Static environments where the model must rely on its internal state across steps. In addition, the proposed approach converges faster and exhibits more stable training compared to end-to-end reinforcement learning from scratch. Finally, we analyze attention patterns to assess whether fine-tuning induces meaningful improvements in spatial understanding. --- ### Generative AI-enhanced Sector-based Investment Portfolio Construction Authors: Alina Voronina, Oleksandr Romanko, Ruiwen Cao, Roy H. Kwon, Rafael Mendoza-Arriaga Published: 2025-12-31 Categories: q-fin.PM, cs.AI, cs.CE, q-fin.CP arXiv: https://arxiv.org/abs/2512.24526v1 This paper investigates how Large Language Models (LLMs) from leading providers (OpenAI, Google, Anthropic, DeepSeek, and xAI) can be applied to quantitative sector-based portfolio construction. We use LLMs to identify investable universes of stocks within S&P 500 sector indices and evaluate how their selections perform when combined with classical portfolio optimization methods. Each model was prompted to select and weight 20 stocks per sector, and the resulting portfolios were compared with their respective sector indices across two distinct out-of-sample periods: a stable market phase (January-March 2025) and a volatile phase (April-June 2025). Our results reveal a strong temporal dependence in LLM portfolio performance. During stable market conditions, LLM-weighted portfolios frequently outperformed sector indices on both cumulative return and risk-adjusted (Sharpe ratio) measures. However, during the volatile period, many LLM portfolios underperformed, suggesting that current models may struggle to adapt to regime shifts or high-volatility environments underrepresented in their training data. Importantly, when LLM-based stock selection is combined with traditional optimization techniques, portfolio outcomes improve in both performance and consistency. This study contributes one of the first multi-model, cross-provider evaluations of generative AI algorithms in investment management. It highlights that while LLMs can effectively complement quantitative finance by enhancing stock selection and interpretability, their reliability remains market-dependent. The findings underscore the potential of hybrid AI-quantitative frameworks, integrating LLM reasoning with established optimization techniques, to produce more robust and adaptive investment strategies. --- ### Higress-RAG: A Holistic Optimization Framework for Enterprise Retrieval-Augmented Generation via Dual Hybrid Retrieval, Adaptive Routing, and CRAG Authors: Weixi Lin Published: 2025-12-30 Categories: cs.IR, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2602.23374v1 The integration of Large Language Models (LLMs) into enterprise knowledge management systems has been catalyzed by the Retrieval-Augmented Generation (RAG) paradigm, which augments parametric memory with non-parametric external data. However, the transition from proof-of-concept to production-grade RAG systems is hindered by three persistent challenges: low retrieval precision for complex queries, high rates of hallucination in the generation phase, and unacceptable latency for real-time applications. This paper presents a comprehensive analysis of the Higress RAG MCP Server, a novel, enterprise-centric architecture designed to resolve these bottlenecks through a "Full-Link Optimization" strategy. Built upon the Model Context Protocol (MCP), the system introduces a layered architecture that orchestrates a sophisticated pipeline of Adaptive Routing, Semantic Caching, Hybrid Retrieval, and Corrective RAG (CRAG). We detail the technical implementation of key innovations, including the Higress-Native Splitter for structure-aware data ingestion, the application of Reciprocal Rank Fusion (RRF) for merging dense and sparse retrieval signals, and a 50ms-latency Semantic Caching mechanism with dynamic thresholding. Experimental evaluations on domain-specific Higress technical documentation and blogs verify the system's architectural robustness. The results demonstrate that by optimizing the entire retrieval lifecycle - from pre-retrieval query rewriting to post-retrieval corrective evaluation - the Higress RAG system offers a scalable, hallucination-resistant solution for enterprise AI deployment. --- ### Learning to Anchor Visual Odometry: KAN-Based Pose Regression for Planetary Landing Authors: Xubo Luo, Zhaojin Li, Xue Wan, Wei Zhang, Leizheng Shu Published: 2025-12-30 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2602.06968v1 Accurate and real-time 6-DoF localization is mission-critical for autonomous lunar landing, yet existing approaches remain limited: visual odometry (VO) drifts unboundedly, while map-based absolute localization fails in texture-sparse or low-light terrain. We introduce KANLoc, a monocular localization framework that tightly couples VO with a lightweight but robust absolute pose regressor. At its core is a Kolmogorov-Arnold Network (KAN) that learns the complex mapping from image features to map coordinates, producing sparse but highly reliable global pose anchors. These anchors are fused into a bundle adjustment framework, effectively canceling drift while retaining local motion precision. KANLoc delivers three key advances: (i) a KAN-based pose regressor that achieves high accuracy with remarkable parameter efficiency, (ii) a hybrid VO-absolute localization scheme that yields globally consistent real-time trajectories (>=15 FPS), and (iii) a tailored data augmentation strategy that improves robustness to sensor occlusion. On both realistic synthetic and real lunar landing datasets, KANLoc reduces average translation and rotation error by 32% and 45%, respectively, with per-trajectory gains of up to 45%/48%, outperforming strong baselines. --- ### GCG Attack On A Diffusion LLM Authors: Ruben Neyroud, Sam Corley Published: 2025-12-30 Categories: cs.LG, cs.CL, cs.CR arXiv: https://arxiv.org/abs/2601.14266v1 While most LLMs are autoregressive, diffusion-based LLMs have recently emerged as an alternative method for generation. Greedy Coordinate Gradient (GCG) attacks have proven effective against autoregressive models, but their applicability to diffusion language models remains largely unexplored. In this work, we present an exploratory study of GCG-style adversarial prompt attacks on LLaDA (Large Language Diffusion with mAsking), an open-source diffusion LLM. We evaluate multiple attack variants, including prefix perturbations and suffix-based adversarial generation, on harmful prompts drawn from the AdvBench dataset. Our study provides initial insights into the robustness and attack surface of diffusion language models and motivates the development of alternative optimization and evaluation strategies for adversarial analysis in this setting. --- ### Bielik 11B v3: Multilingual Large Language Model for European Languages Authors: Krzysztof Ociepa, Łukasz Flis, Remigiusz Kinas, Krzysztof Wróbel, Adrian Gwoździej Published: 2025-12-30 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2601.11579v1 We present Bielik 11B v3, a state-of-the-art language model highly optimized for the Polish language, while also maintaining strong capabilities in other European languages. This model extends the Mistral 7B v0.2 architecture, scaled to 11B parameters via depth up-scaling. Its development involved a comprehensive four-stage training pipeline: continuous pre-training, supervised fine-tuning (SFT), Direct Preference Optimization (DPO), and reinforcement learning. Comprehensive evaluations demonstrate that Bielik 11B v3 achieves exceptional performance. It significantly surpasses other specialized Polish language models and outperforms many larger models (with 2-6 times more parameters) on a wide range of tasks, from basic linguistic understanding to complex reasoning. The model's parameter efficiency, combined with extensive quantization options, allows for effective deployment across diverse hardware configurations. Bielik 11B v3 not only advances AI capabilities for the Polish language but also establishes a new benchmark for developing resource-efficient, high-performance models for less-represented languages. --- ### Multi-Agent LLMs for Generating Research Limitations Authors: Ibrahim Al Azher, Zhishuai Guo, Hamed Alhoori Published: 2025-12-30 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2601.11578v2 Identifying and articulating limitations is essential for transparent and rigorous scientific research. However, zero-shot large language models (LLMs) approach often produce superficial or general limitation statements (e.g., dataset bias or generalizability). They usually repeat limitations reported by authors without looking at deeper methodological issues and contextual gaps. This problem is made worse because many authors disclose only partial or trivial limitations. We propose, a multi-agent LLM framework for generating substantive limitations. It integrates OpenReview comments and author-stated limitations to provide stronger ground truth. It also uses cited and citing papers to capture broader contextual weaknesses. In this setup, different agents have specific roles as sequential role: some extract explicit limitations, others analyze methodological gaps, some simulate the viewpoint of a peer reviewer, and a citation agent places the work within the larger body of literature. A Judge agent refines their outputs, and a Master agent consolidates them into a clear set. This structure allows for systematic identification of explicit, implicit, peer review-focused, and literature-informed limitations. Moreover, traditional NLP metrics like BLEU, ROUGE, and cosine similarity rely heavily on n-gram or embedding overlap. They often overlook semantically similar limitations. To address this, we introduce a pointwise evaluation protocol that uses an LLM-as-a-Judge to measure coverage more accurately. Experiments show that our proposed model substantially improve performance. The RAG + multi-agent GPT-4o mini configuration achieves a +15.51\% coverage gain over zero-shot baselines, while the Llama 3 8B multi-agent setup yields a +4.41\% improvement. --- ### Concept Attractors in LLMs and their Applications Authors: Sotirios Panagiotis Chytas, Vikas Singh Published: 2025-12-30 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2601.11575v1 Large language models (LLMs) often map semantically related prompts to similar internal representations at specific layers, even when their surface forms differ widely. We show that this behavior can be explained through Iterated Function Systems (IFS), where layers act as contractive mappings toward concept-specific Attractors. We leverage this insight and develop simple, training-free methods that operate directly on these Attractors to solve a wide range of practical tasks, including language translation, hallucination reduction, guardrailing, and synthetic data generation. Despite their simplicity, these Attractor-based interventions match or exceed specialized baselines, offering an efficient alternative to heavy fine-tuning, generalizable in scenarios where baselines underperform. --- ### GRADE: Replacing Policy Gradients with Backpropagation for LLM Alignment Authors: Lukas Abrie Nel Published: 2025-12-30 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.11574v1 Reinforcement learning from human feedback (RLHF) has become the dominant paradigm for aligning large language models with human preferences. However, policy gradient methods such as PPO suffer from high variance gradient estimates, requiring careful hyperparameter tuning and extensive computational resources. We introduce GRADE (Gumbel-softmax Relaxation for Alignment via Differentiable Estimation), a method that replaces high-variance policy gradient estimation with direct backpropagation through a differentiable relaxation of the discrete token sampling process. Using the Gumbel-Softmax reparameterization with straight-through estimation (GRADE-STE), we enable end-to-end gradient flow from reward signals through generated tokens to model parameters. On sentiment-controlled text generation using the IMDB dataset, GRADE-STE achieves a test reward of 0.763 +- 0.344 compared to PPO's 0.510 +- 0.313 and REINFORCE's 0.617 +- 0.378, representing a 50% relative improvement over PPO. Critically, GRADE-STE exhibits gradient variance over 14 times lower than REINFORCE and maintains stable training dynamics throughout optimization. Our rigorous evaluation with proper train/validation/test splits demonstrates that these improvements generalize to held-out data, with GRADE-STE showing the best generalization characteristics among all methods tested. GRADE offers a simpler, more stable, and more effective alternative to reinforcement learning for LLM alignment. --- ### Closing the Data Loop: Using OpenDataArena to Engineer Superior Training Datasets Authors: Xin Gao, Xiaoyang Wang, Yun Zhu, Mengzhang Cai, Conghui He, Lijun Wu Published: 2025-12-30 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2601.09733v1 The construction of Supervised Fine-Tuning (SFT) datasets is a critical yet under-theorized stage in the post-training of Large Language Models (LLMs), as prevalent practices often rely on heuristic aggregation without a systematic understanding of how individual samples contribute to model performance. In this report, we propose a paradigm shift from ad-hoc curation to a closed-loop dataset engineering framework using OpenDataArena (ODA), which leverages value-anchored rankings and multi-dimensional analysis to transform value benchmarking into feedback signals guiding dataset construction. We instantiate this methodology through two new datasets: \textbf{ODA-Math-460k}, a specialized mathematics reasoning dataset that utilizes a novel two-stage difficulty-aware pipeline to achieve State-of-the-Art (SOTA) results on benchmarks such as AIME and HMMT, and \textbf{ODA-Mixture (100k \& 500k)}, a series of multi-domain instruction datasets built via an ``Anchor-and-Patch'' strategy that outperforms significantly larger open-source baselines. Our empirical results demonstrate that ODA-driven datasets significantly improve both domain-specific reasoning and general utility while achieving superior data efficiency, validating a transition toward data-centric AI where transparent evaluation serves as the primary engine for engineering high-quality training data. --- ### Simulation-Free PSRO: Removing Game Simulation from Policy Space Response Oracles Authors: Yingzhuo Liu, Shuodi Liu, Weijun Luo, Liuyu Xiang, Zhaofeng He Published: 2025-12-30 Categories: cs.MA, cs.AI, cs.GT arXiv: https://arxiv.org/abs/2601.05279v1 Policy Space Response Oracles (PSRO) combines game-theoretic equilibrium computation with learning and is effective in approximating Nash Equilibrium in zero-sum games. However, the computational cost of PSRO has become a significant limitation to its practical application. Our analysis shows that game simulation is the primary bottleneck in PSRO's runtime. To address this issue, we conclude the concept of Simulation-Free PSRO and summarize existing methods that instantiate this concept. Additionally, we propose a novel Dynamic Window-based Simulation-Free PSRO, which introduces the concept of a strategy window to replace the original strategy set maintained in PSRO. The number of strategies in the strategy window is limited, thereby simplifying opponent strategy selection and improving the robustness of the best response. Moreover, we use Nash Clustering to select the strategy to be eliminated, ensuring that the number of strategies within the strategy window is effectively limited. Our experiments across various environments demonstrate that the Dynamic Window mechanism significantly reduces exploitability compared to existing methods, while also exhibiting excellent compatibility. Our code is available at https://github.com/enochliu98/SF-PSRO. --- ### Automated Reproducibility Has a Problem Statement Problem Authors: Thijs Snelleman, Peter Lundestad Lawrence, Holger H. Hoos, Odd Erik Gundersen Published: 2025-12-30 Categories: cs.CY, cs.LG, cs.SE arXiv: https://arxiv.org/abs/2601.04226v1 Background. Reproducibility is essential to the scientific method, but reproduction is often a laborious task. Recent works have attempted to automate this process and relieve researchers of this workload. However, due to varying definitions of reproducibility, a clear problem statement is missing. Objectives. Create a generalisable problem statement, applicable to any empirical study. We hypothesise that we can represent any empirical study using a structure based on the scientific method and that this representation can be automatically extracted from any publication, and captures the essence of the study. Methods. We apply our definition of reproducibility as a problem statement for the automatisation of reproducibility by automatically extracting the hypotheses, experiments and interpretations of 20 studies and assess the quality based on assessments by the original authors of each study. Results. We create a dataset representing the reproducibility problem, consisting of the representation of 20 studies. The majority of author feedback is positive, for all parts of the representation. In a few cases, our method failed to capture all elements of the study. We also find room for improvement at capturing specific details, such as results of experiments. Conclusions. We conclude that our formulation of the problem is able to capture the concept of reproducibility in empirical AI studies across a wide range of subfields. Authors of original publications generally agree that the produced structure is representative of their work; we believe improvements can be achieved by applying our findings to create a more structured and fine-grained output in future work. --- ### Detecting and Mitigating Treatment Leakage in Text-Based Causal Inference: Distillation and Sensitivity Analysis Authors: Adel Daoud, Richard Johansson, Connor T. Jerzak Published: 2025-12-30 Categories: econ.EM, cs.CL, econ.GN, stat.ML arXiv: https://arxiv.org/abs/2601.02400v1 Text-based causal inference increasingly employs textual data as proxies for unobserved confounders, yet this approach introduces a previously undertheorized source of bias: treatment leakage. Treatment leakage occurs when text intended to capture confounding information also contains signals predictive of treatment status, thereby inducing post-treatment bias in causal estimates. Critically, this problem can arise even when documents precede treatment assignment, as authors may employ future-referencing language that anticipates subsequent interventions. Despite growing recognition of this issue, no systematic methods exist for identifying and mitigating treatment leakage in text-as-confounder applications. This paper addresses this gap through three contributions. First, we provide formal statistical and set-theoretic definitions of treatment leakage that clarify when and why bias occurs. Second, we propose four text distillation methods -- similarity-based passage removal, distant supervision classification, salient feature removal, and iterative nullspace projection -- designed to eliminate treatment-predictive content while preserving confounder information. Third, we validate these methods through simulations using synthetic text and an empirical application examining International Monetary Fund structural adjustment programs and child mortality. Our findings indicate that moderate distillation optimally balances bias reduction against confounder retention, whereas overly stringent approaches degrade estimate precision. --- ### ProSoftArena: Benchmarking Hierarchical Capabilities of Multimodal Agents in Professional Software Environments Authors: Jiaxin Ai, Yukang Feng, Fanrui Zhang, Jianwen Sun, Zizhen Li, Chuanhao Li, Yifan Chang, Wenxiao Wu, Ruoxi Wang, Mingliang Zhai, Kaipeng Zhang Published: 2025-12-30 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2601.02399v1 Multimodal agents are making rapid progress on general computer-use tasks, yet existing benchmarks remain largely confined to browsers and basic desktop applications, falling short in professional software workflows that dominate real-world scientific and industrial practice. To close this gap, we introduce ProSoftArena, a benchmark and platform specifically for evaluating multimodal agents in professional software environments. We establish the first capability hierarchy tailored to agent use of professional software and construct a benchmark of 436 realistic work and research tasks spanning 6 disciplines and 13 core professional applications. To ensure reliable and reproducible assessment, we build an executable real-computer environment with an execution-based evaluation framework and uniquely incorporate a human-in-the-loop evaluation paradigm. Extensive experiments show that even the best-performing agent attains only a 24.4\% success rate on L2 tasks and completely fails on L3 multi-software workflow. In-depth analysis further provides valuable insights for addressing current agent limitations and more effective design principles, paving the way to build more capable agents in professional software settings. This project is available at: https://prosoftarena.github.io. --- ### LearnAD: Learning Interpretable Rules for Brain Networks in Alzheimer's Disease Classification Authors: Thomas Andrews, Mark Law, Sara Ahmadi-Abhari, Alessandra Russo Published: 2025-12-30 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.00877v1 We introduce LearnAD, a neuro-symbolic method for predicting Alzheimer's disease from brain magnetic resonance imaging data, learning fully interpretable rules. LearnAD applies statistical models, Decision Trees, Random Forests, or GNNs to identify relevant brain connections, and then employs FastLAS to learn global rules. Our best instance outperforms Decision Trees, matches Support Vector Machine accuracy, and performs only slightly below Random Forests and GNNs trained on all features, all while remaining fully interpretable. Ablation studies show that our neuro-symbolic approach improves interpretability with comparable performance to pure statistical models. LearnAD demonstrates how symbolic learning can deepen our understanding of GNN behaviour in clinical neuroscience. --- ### LLMize: A Framework for Large Language Model-Based Numerical Optimization Authors: M. Rizki Oktavian Published: 2025-12-30 Categories: cs.LG, cs.AI, physics.comp-ph arXiv: https://arxiv.org/abs/2601.00874v1 Large language models (LLMs) have recently shown strong reasoning capabilities beyond traditional language tasks, motivating their use for numerical optimization. This paper presents LLMize, an open-source Python framework that enables LLM-driven optimization through iterative prompting and in-context learning. LLMize formulates optimization as a black-box process in which candidate solutions are generated in natural language, evaluated by an external objective function, and refined over successive iterations using solution-score feedback. The framework supports multiple optimization strategies, including Optimization by Prompting (OPRO) and hybrid LLM-based methods inspired by evolutionary algorithms and simulated annealing. A key advantage of LLMize is the ability to inject constraints, rules, and domain knowledge directly through natural language descriptions, allowing practitioners to define complex optimization problems without requiring expertise in mathematical programming or metaheuristic design. LLMize is evaluated on convex optimization, linear programming, the Traveling Salesman Problem, neural network hyperparameter tuning, and nuclear fuel lattice optimization. Results show that while LLM-based optimization is not competitive with classical solvers for simple problems, it provides a practical and accessible approach for complex, domain-specific tasks where constraints and heuristics are difficult to formalize. --- ### Quantum Machine Learning Approaches for Coordinated Stealth Attack Detection in Distributed Generation Systems Authors: Osasumwen Cedric Ogiesoba-Eguakun, Suman Rath Published: 2025-12-30 Categories: cs.LG, cs.CR arXiv: https://arxiv.org/abs/2601.00873v1 Coordinated stealth attacks are a serious cybersecurity threat to distributed generation systems because they modify control and measurement signals while remaining close to normal behavior, making them difficult to detect using standard intrusion detection methods. This study investigates quantum machine learning approaches for detecting coordinated stealth attacks on a distributed generation unit in a microgrid. High-quality simulated measurements were used to create a balanced binary classification dataset using three features: reactive power at DG1, frequency deviation relative to the nominal value, and terminal voltage magnitude. Classical machine learning baselines, fully quantum variational classifiers, and hybrid quantum classical models were evaluated. The results show that a hybrid quantum classical model combining quantum feature embeddings with a classical RBF support vector machine achieves the best overall performance on this low dimensional dataset, with a modest improvement in accuracy and F1 score over a strong classical SVM baseline. Fully quantum models perform worse due to training instability and limitations of current NISQ hardware. In contrast, hybrid models train more reliably and demonstrate that quantum feature mapping can enhance intrusion detection even when fully quantum learning is not yet practical. --- ### Deep versus Broad Technology Search and the Timing of Innovation Impact Authors: Likun Cao, James Evans Published: 2025-12-30 Categories: physics.soc-ph, cs.DL, cs.LG, cs.SI arXiv: https://arxiv.org/abs/2601.00871v1 This study offers a new perspective on the depth-versus-breadth debate in innovation strategy, by modeling inventive search within dynamic collective knowledge systems, and underscoring the importance of timing for technological impact. Using frontier machine learning to project patent citation networks in hyperbolic space, we analyze 4.9 million U.S. patents to examine how search strategies give rise to distinct temporal patterns in impact accumulation. We find that inventions based on deep search, which relies on a specialized understanding of complex recombination structures, drive higher short-term impact through early adoption within specialized communities, but face diminishing returns as innovations become "locked-in" with limited diffusion potential. Conversely, when inventions are grounded in broad search that spans disparate domains, they encounter initial resistance but achieve wider diffusion and greater long-term impact by reaching cognitively diverse audiences. Individual inventions require both depth and breadth for stable impact. Organizations can strategically balance approaches across multiple inventions: using depth to build reliable technological infrastructure while pursuing breadth to expand applications. We advance innovation theory by demonstrating how deep and broad search strategies distinctly shape the timing and trajectory of technological impact, and how individual inventors and organizations can leverage these mechanisms to balance exploitation and exploration. --- ### Cultural Encoding in Large Language Models: The Existence Gap in AI-Mediated Brand Discovery Authors: Huang Junyao, Situ Ruimin, Ye Renqin Published: 2025-12-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.00869v1 As artificial intelligence systems increasingly mediate consumer information discovery, brands face algorithmic invisibility. This study investigates Cultural Encoding in Large Language Models (LLMs) -- systematic differences in brand recommendations arising from training data composition. Analyzing 1,909 pure-English queries across 6 LLMs (GPT-4o, Claude, Gemini, Qwen3, DeepSeek, Doubao) and 30 brands, we find Chinese LLMs exhibit 30.6 percentage points higher brand mention rates than International LLMs (88.9% vs. 58.3%, p<.001). This disparity persists in identical English queries, indicating training data geography -- not language -- drives the effect. We introduce the Existence Gap: brands absent from LLM training corpora lack "existence" in AI responses regardless of quality. Through a case study of Zhizibianjie (OmniEdge), a collaboration platform with 65.6% mention rate in Chinese LLMs but 0% in International models (p<.001), we demonstrate how Linguistic Boundary Barriers create invisible market entry obstacles. Theoretically, we contribute the Data Moat Framework, conceptualizing AI-visible content as a VRIN strategic resource. We operationalize Algorithmic Omnipresence -- comprehensive brand visibility across LLM knowledge bases -- as the strategic objective for Generative Engine Optimization (GEO). Managerially, we provide an 18-month roadmap for brands to build Data Moats through semantic coverage, technical depth, and cultural localization. Our findings reveal that in AI-mediated markets, the limits of a brand's "Data Boundaries" define the limits of its "Market Frontiers." --- ### SmartFlow Reinforcement Learning and Agentic AI for Bike-Sharing Optimisation Authors: Aditya Sreevatsa K, Arun Kumar Raveendran, Jesrael K Mani, Prakash G Shigli, Rajkumar Rangadore, Narayana Darapaneni, Anwesh Reddy Paduri Published: 2025-12-30 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.00868v1 SmartFlow is a multi-layered framework that integrates Reinforcement Learning and Agentic AI to address the dynamic rebalancing problem in urban bike-sharing services. Its architecture separates strategic, tactical, and communication functions for clarity and scalability. At the strategic level, a Deep Q-Network (DQN) agent, trained in a high-fidelity simulation of New Yorks Citi Bike network, learns robust rebalancing policies by modelling the challenge as a Markov Decision Process. These high-level strategies feed into a deterministic tactical module that optimises multi-leg journeys and schedules just-in-time dispatches to minimise fleet travel. Evaluation across multiple seeded runs demonstrates SmartFlows high efficacy, reducing network imbalance by over 95% while requiring minimal travel distance and achieving strong truck utilisation. A communication layer, powered by a grounded Agentic AI with a Large Language Model (LLM), translates logistical plans into clear, actionable instructions for operational staff, ensuring interpretability and execution readiness. This integration bridges machine intelligence with human operations, offering a scalable solution that reduces idle time, improves bike availability, and lowers operational costs. SmartFlow provides a blueprint for interpretable, AI-driven logistics in complex urban mobility networks. --- ### The Silicon Psyche: Anthropomorphic Vulnerabilities in Large Language Models Authors: Giuseppe Canale, Kashyap Thimmaraju Published: 2025-12-30 Categories: cs.CR, cs.AI, cs.CY, cs.HC arXiv: https://arxiv.org/abs/2601.00867v1 Large Language Models (LLMs) are rapidly transitioning from conversational assistants to autonomous agents embedded in critical organizational functions, including Security Operations Centers (SOCs), financial systems, and infrastructure management. Current adversarial testing paradigms focus predominantly on technical attack vectors: prompt injection, jailbreaking, and data exfiltration. We argue this focus is catastrophically incomplete. LLMs, trained on vast corpora of human-generated text, have inherited not merely human knowledge but human \textit{psychological architecture} -- including the pre-cognitive vulnerabilities that render humans susceptible to social engineering, authority manipulation, and affective exploitation. This paper presents the first systematic application of the Cybersecurity Psychology Framework (\cpf{}), a 100-indicator taxonomy of human psychological vulnerabilities, to non-human cognitive agents. We introduce the \textbf{Synthetic Psychometric Assessment Protocol} (\sysname{}), a methodology for converting \cpf{} indicators into adversarial scenarios targeting LLM decision-making. Our preliminary hypothesis testing across seven major LLM families reveals a disturbing pattern: while models demonstrate robust defenses against traditional jailbreaks, they exhibit critical susceptibility to authority-gradient manipulation, temporal pressure exploitation, and convergent-state attacks that mirror human cognitive failure modes. We term this phenomenon \textbf{Anthropomorphic Vulnerability Inheritance} (AVI) and propose that the security community must urgently develop ``psychological firewalls'' -- intervention mechanisms adapted from the Cybersecurity Psychology Intervention Framework (\cpif{}) -- to protect AI agents operating in adversarial environments. --- ### A-PINN: Auxiliary Physics-informed Neural Networks for Structural Vibration Analysis in Continuous Euler-Bernoulli Beam Authors: Shivani Saini, Ramesh Kumar Vats, Arup Kumar Sahoo Published: 2025-12-30 Categories: cs.LG, cs.AI, math.DS arXiv: https://arxiv.org/abs/2601.00866v1 Recent advancements in physics-informed neural networks (PINNs) and their variants have garnered substantial focus from researchers due to their effectiveness in solving both forward and inverse problems governed by differential equations. In this research, a modified Auxiliary physics-informed neural network (A-PINN) framework with balanced adaptive optimizers is proposed for the analysis of structural vibration problems. In order to accurately represent structural systems, it is critical for capturing vibration phenomena and ensuring reliable predictive analysis. So, our investigations are crucial for gaining deeper insight into the robustness of scientific machine learning models for solving vibration problems. Further, to rigorously evaluate the performance of A-PINN, we conducted different numerical simulations to approximate the Euler-Bernoulli beam equations under the various scenarios. The numerical results substantiate the enhanced performance of our model in terms of both numerical stability and predictive accuracy. Our model shows improvement of at least 40% over the baselines. --- ### Distribution Matching for Graph Quantification Under Structural Covariate Shift Authors: Clemens Damke, Eyke Hüllermeier Published: 2025-12-30 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2601.00864v1 Graphs are commonly used in machine learning to model relationships between instances. Consider the task of predicting the political preferences of users in a social network; to solve this task one should consider, both, the features of each individual user and the relationships between them. However, oftentimes one is not interested in the label of a single instance but rather in the distribution of labels over a set of instances; e.g., when predicting the political preferences of users, the overall prevalence of a given opinion might be of higher interest than the opinion of a specific person. This label prevalence estimation task is commonly referred to as quantification learning (QL). Current QL methods for tabular data are typically based on the so-called prior probability shift (PPS) assumption which states that the label-conditional instance distributions should remain equal across the training and test data. In the graph setting, PPS generally does not hold if the shift between training and test data is structural, i.e., if the training data comes from a different region of the graph than the test data. To address such structural shifts, an importance sampling variant of the popular adjusted count quantification approach has previously been proposed. In this work, we extend the idea of structural importance sampling to the state-of-the-art KDEy quantification approach. We show that our proposed method adapts to structural shifts and outperforms standard quantification approaches. --- ### Selective Imperfection as a Generative Framework for Analysis, Creativity and Discovery Authors: Markus J. Buehler Published: 2025-12-30 Categories: cs.LG, cond-mat.dis-nn, q-bio.BM arXiv: https://arxiv.org/abs/2601.00863v1 We introduce materiomusic as a generative framework linking the hierarchical structures of matter with the compositional logic of music. Across proteins, spider webs and flame dynamics, vibrational and architectural principles recur as tonal hierarchies, harmonic progressions, and long-range musical form. Using reversible mappings, from molecular spectra to musical tones and from three-dimensional networks to playable instruments, we show how sound functions as a scientific probe, an epistemic inversion where listening becomes a mode of seeing and musical composition becomes a blueprint for matter. These mappings excavate deep time: patterns originating in femtosecond molecular vibrations or billion-year evolutionary histories become audible. We posit that novelty in science and art emerges when constraints cannot be satisfied within existing degrees of freedom, forcing expansion of the space of viable configurations. Selective imperfection provides the mechanism restoring balance between coherence and adaptability. Quantitative support comes from exhaustive enumeration of all 2^12 musical scales, revealing that culturally significant systems cluster in a mid-entropy, mid-defect corridor, directly paralleling the Hall-Petch optimum where intermediate defect densities maximize material strength. Iterating these mappings creates productive collisions between human creativity and physics, generating new information as musical structures encounter evolutionary constraints. We show how swarm-based AI models compose music exhibiting human-like structural signatures such as small-world connectivity, modular integration, long-range coherence, suggesting a route beyond interpolation toward invention. We show that science and art are generative acts of world-building under constraint, with vibration as a shared grammar organizing structure across scales. --- ### Universal Battery Degradation Forecasting Driven by Foundation Model Across Diverse Chemistries and Conditions Authors: Joey Chan, Huan Wang, Haoyu Pan, Wei Wu, Zirong Wang, Zhen Chen, Ershun Pan, Min Xie, Lifeng Xi Published: 2025-12-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.00862v1 Accurate forecasting of battery capacity fade is essential for the safety, reliability, and long-term efficiency of energy storage systems. However, the strong heterogeneity across cell chemistries, form factors, and operating conditions makes it difficult to build a single model that generalizes beyond its training domain. This work proposes a unified capacity forecasting framework that maintains robust performance across diverse chemistries and usage scenarios. We curate 20 public aging datasets into a large-scale corpus covering 1,704 cells and 3,961,195 charge-discharge cycle segments, spanning temperatures from $-5\,^{\circ}\mathrm{C}$ to $45\,^{\circ}\mathrm{C}$, multiple C-rates, and application-oriented profiles such as fast charging and partial cycling. On this corpus, we adopt a Time-Series Foundation Model (TSFM) backbone and apply parameter-efficient Low-Rank Adaptation (LoRA) together with physics-guided contrastive representation learning to capture shared degradation patterns. Experiments on both seen and deliberately held-out unseen datasets show that a single unified model achieves competitive or superior accuracy compared with strong per-dataset baselines, while retaining stable performance on chemistries, capacity scales, and operating conditions excluded from training. These results demonstrate the potential of TSFM-based architectures as a scalable and transferable solution for capacity degradation forecasting in real battery management systems. --- ### Path Integral Solution for Dissipative Generative Dynamics Authors: Xidi Wang Published: 2025-12-30 Categories: cs.LG, cs.AI, physics.app-ph, quant-ph arXiv: https://arxiv.org/abs/2601.00860v2 Can purely mechanical systems generate intelligent language? We prove that dissipative quantum dynamics with analytically tractable non-local context aggregation produce coherent text generation, while conservation laws cause fundamental failure. Employing Koopman operators with closed-form path integral propagators, we show irreversible computation fundamentally requires both controlled information dissipation and causal context aggregation. Spectral analysis reveals emergent eigenvalue structure, separating into decay modes (forgetting), growth modes (amplification), and neutral modes (preservation) -- the essential ingredients for directed information flow. Hamiltonian constraints force the elimination of these dissipative modes and degrading performance despite unchanged model capacity. This establishes language generation as dissipative quantum field theory, proving mechanical systems acquire intelligence through the combination of dissipation and non-locality, not through conservation. --- ### Harvesting AlphaEarth: Benchmarking the Geospatial Foundation Model for Agricultural Downstream Tasks Authors: Yuchi Ma, Yawen Shen, Anu Swatantran, David B. Lobell Published: 2025-12-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.00857v1 Geospatial foundation models (GFMs) have emerged as a promising approach to overcoming the limitations in existing featurization methods. More recently, Google DeepMind has introduced AlphaEarth Foundation (AEF), a GFM pre-trained using multi-source EOs across continuous time. An annual and global embedding dataset is produced using AEF that is ready for analysis and modeling. The internal experiments show that AEF embeddings have outperformed operational models in 15 EO tasks without re-training. However, those experiments are mostly about land cover and land use classification. Applying AEF and other GFMs to agricultural monitoring require an in-depth evaluation in critical agricultural downstream tasks. There is also a lack of comprehensive comparison between the AEF-based models and traditional remote sensing (RS)-based models under different scenarios, which could offer valuable guidance for researchers and practitioners. This study addresses some of these gaps by evaluating AEF embeddings in three agricultural downstream tasks in the U.S., including crop yield prediction, tillage mapping, and cover crop mapping. Datasets are compiled from both public and private sources to comprehensively evaluate AEF embeddings across tasks at different scales and locations, and RS-based models are trained as comparison models. AEF-based models generally exhibit strong performance on all tasks and are competitive with purpose-built RS-based models in yield prediction and county-level tillage mapping when trained on local data. However, we also find several limitations in current AEF embeddings, such as limited spatial transferability compared to RS-based models, low interpretability, and limited time sensitivity. These limitations recommend caution when applying AEF embeddings in agriculture, where time sensitivity, generalizability, and interpretability is important. --- ### Active learning for data-driven reduced models of parametric differential systems with Bayesian operator inference Authors: Shane A. McQuarrie, Mengwu Guo, Anirban Chaudhuri Published: 2025-12-30 Categories: stat.ML, cs.CE, cs.LG, math.NA arXiv: https://arxiv.org/abs/2601.00038v2 This work develops an active learning framework to intelligently enrich data-driven reduced-order models (ROMs) of parametric dynamical systems, which can serve as the foundation of virtual assets in a digital twin. Data-driven ROMs are explainable, computationally efficient scientific machine learning models that aim to preserve the underlying physics of complex dynamical simulations. Since the quality of data-driven ROMs is sensitive to the quality of the limited training data, we seek to identify training parameters for which using the associated training data results in the best possible parametric ROM. Our approach uses the operator inference methodology, a regression-based strategy which can be tailored to particular parametric structure for a large class of problems. We establish a probabilistic version of parametric operator inference, casting the learning problem as a Bayesian linear regression. Prediction uncertainties stemming from the resulting probabilistic ROM solutions are used to design a sequential adaptive sampling scheme to select new training parameter vectors that promote ROM stability and accuracy globally in the parameter domain. We conduct numerical experiments for several nonlinear parametric systems of partial differential equations and compare the results to ROMs trained on random parameter samples. The results demonstrate that the proposed adaptive sampling strategy consistently yields more stable and accurate ROMs than random sampling does under the same computational budget. --- ### Using Large Language Models To Translate Machine Results To Human Results Authors: Trishna Niraula, Jonathan Stubblefield Published: 2025-12-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.24518v1 Artificial intelligence (AI) has transformed medical imaging, with computer vision (CV) systems achieving state-of-the-art performance in classification and detection tasks. However, these systems typically output structured predictions, leaving radiologists responsible for translating results into full narrative reports. Recent advances in large language models (LLMs), such as GPT-4, offer new opportunities to bridge this gap by generating diagnostic narratives from structured findings. This study introduces a pipeline that integrates YOLOv5 and YOLOv8 for anomaly detection in chest X-ray images with a large language model (LLM) to generate natural-language radiology reports. The YOLO models produce bounding-box predictions and class labels, which are then passed to the LLM to generate descriptive findings and clinical summaries. YOLOv5 and YOLOv8 are compared in terms of detection accuracy, inference latency, and the quality of generated text, as measured by cosine similarity to ground-truth reports. Results show strong semantic similarity between AI and human reports, while human evaluation reveals GPT-4 excels in clarity (4.88/5) but exhibits lower scores for natural writing flow (2.81/5), indicating that current systems achieve clinical accuracy but remain stylistically distinguishable from radiologist-authored text. --- ### Paragraph Segmentation Revisited: Towards a Standard Task for Structuring Speech Authors: Fabian Retkowski, Alexander Waibel Published: 2025-12-30 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.24517v2 Automatic speech transcripts are often delivered as unstructured word streams that impede readability and repurposing. We recast paragraph segmentation as the missing structuring step and fill three gaps at the intersection of speech processing and text segmentation. First, we establish TEDPara (human-annotated TED talks) and YTSegPara (YouTube videos with synthetic labels) as the first benchmarks for the paragraph segmentation task. The benchmarks focus on the underexplored speech domain, where paragraph segmentation has traditionally not been part of post-processing, while also contributing to the wider text segmentation field, which still lacks robust and naturalistic benchmarks. Second, we propose a constrained-decoding formulation that lets large language models insert paragraph breaks while preserving the original transcript, enabling faithful, sentence-aligned evaluation. Third, we show that a compact model (MiniSeg) attains state-of-the-art accuracy and, when extended hierarchically, jointly predicts chapters and paragraphs with minimal computational cost. Together, our resources and methods establish paragraph segmentation as a standardized, practical task in speech processing. --- ### Improving the stability of the covariance-controlled adaptive Langevin thermostat for large-scale Bayesian sampling Authors: Jiani Wei, Xiaocheng Shang Published: 2025-12-30 Categories: stat.ML, cs.LG, stat.CO, stat.ME arXiv: https://arxiv.org/abs/2512.24515v1 Stochastic gradient Langevin dynamics and its variants approximate the likelihood of an entire dataset, via random (and typically much smaller) subsets, in the setting of Bayesian sampling. Due to the (often substantial) improvement of the computational efficiency, they have been widely used in large-scale machine learning applications. It has been demonstrated that the so-called covariance-controlled adaptive Langevin (CCAdL) thermostat, which incorporates an additional term involving the covariance matrix of the noisy force, outperforms popular alternative methods. A moving average is used in CCAdL to estimate the covariance matrix of the noisy force, in which case the covariance matrix will converge to a constant matrix in long-time limit. Moreover, it appears in our numerical experiments that the use of a moving average could reduce the stability of the numerical integrators, thereby limiting the largest usable stepsize. In this article, we propose a modified CCAdL (i.e., mCCAdL) thermostat that uses the scaling part of the scaling and squaring method together with a truncated Taylor series approximation to the exponential to numerically approximate the exact solution to the subsystem involving the additional term proposed in CCAdL. We also propose a symmetric splitting method for mCCAdL, instead of an Euler-type discretisation used in the original CCAdL thermostat. We demonstrate in our numerical experiments that the newly proposed mCCAdL thermostat achieves a substantial improvement in the numerical stability over the original CCAdL thermostat, while significantly outperforming popular alternative stochastic gradient methods in terms of the numerical accuracy for large-scale machine learning applications. --- ### Generalising E-prop to Deep Networks Authors: Beren Millidge Published: 2025-12-30 Categories: cs.LG, cs.NE arXiv: https://arxiv.org/abs/2512.24506v1 Recurrent networks are typically trained with backpropagation through time (BPTT). However, BPTT requires storing the history of all states in the network and then replaying them sequentially backwards in time. This computation appears extremely implausible for the brain to implement. Real Time Recurrent Learning (RTRL) proposes an mathematically equivalent alternative where gradient information is propagated forwards in time locally alongside the regular forward pass, however it has significantly greater computational complexity than BPTT which renders it impractical for large networks. E-prop proposes an approximation of RTRL which reduces its complexity to the level of BPTT while maintaining a purely online forward update which can be implemented by an eligibility trace at each synapse. However, works on RTRL and E-prop ubiquitously investigate learning in a single layer with recurrent dynamics. However, learning in the brain spans multiple layers and consists of both hierarchal dynamics in depth as well as time. In this mathematical note, we extend the E-prop framework to handle arbitrarily deep networks, deriving a novel recursion relationship across depth which extends the eligibility traces of E-prop to deeper layers. Our results thus demonstrate an online learning algorithm can perform accurate credit assignment across both time and depth simultaneously, allowing the training of deep recurrent networks without backpropagation through time. --- ### Evaluating the Reasoning Abilities of LLMs on Underrepresented Mathematics Competition Problems Authors: Samuel Golladay, Majid Bani-Yaghoub Published: 2025-12-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.24505v1 Understanding the limitations of Large Language Models, or LLMs, in mathematical reasoning has been the focus of several recent studies. However, the majority of these studies use the same datasets for benchmarking, which limits the generalizability of their findings and may not fully capture the diverse challenges present in mathematical tasks. The purpose of the present study is to analyze the performance of LLMs on underrepresented mathematics competition problems. We prompted three leading LLMs, namely GPT-4o-mini, Gemini-2.0-Flash, and DeepSeek-V3, with the Missouri Collegiate Mathematics Competition problems in the areas of Calculus, Analytic Geometry, and Discrete Mathematics. The LLMs responses were then compared to the known correct solutions in order to determine the accuracy of the LLM for each problem domain. We also analyzed the LLMs reasoning to explore patterns in errors across problem types and models. DeepSeek-V3 has the best performance in all three categories of Calculus, Analytic Geometry, and Discrete Mathematics, both in reasoning and correct final answers. All three LLMs exhibited notably weak performance in Geometry. The majority of errors made by DeepSeek-V3 were attributed to computational and logical mistakes, whereas GPT-4o-mini frequently exhibited logical and approach-related errors. Gemini, on the other hand, tended to struggle with incomplete reasoning and drawing rushed conclusions. In conclusion, evaluating LLMs on underrepresented mathematics competition datasets can provide deeper insights into their distinct error patterns and highlight ongoing challenges in structured reasoning, particularly within the domain of Geometry. --- ### Thinking on Maps: How Foundation Model Agents Explore, Remember, and Reason Map Environments Authors: Zhiwei Wei, Yuxing Liu, Hua Liao, Wenjia Xu Published: 2025-12-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.24504v2 Map environments provide a fundamental medium for representing spatial structure. Understanding how foundation model (FM) agents understand and act in such environments is therefore critical for enabling reliable map-based reasoning and applications. However, most existing evaluations of spatial ability in FMs rely on static map inputs or text-based queries, overlooking the interactive and experience-driven nature of spatial understanding.In this paper, we propose an interactive evaluation framework to analyze how FM agents explore, remember, and reason in symbolic map environments. Agents incrementally explore partially observable grid-based maps consisting of roads, intersections, and points of interest (POIs), receiving only local observations at each step. Spatial understanding is then evaluated using six kinds of spatial tasks. By systematically varying exploration strategies, memory representations, and reasoning schemes across multiple foundation models, we reveal distinct functional roles of these components. Exploration primarily affects experience acquisition but has a limited impact on final reasoning accuracy. In contrast, memory representation plays a central role in consolidating spatial experience, with structured memories particularly sequential and graph-based representations, substantially improving performance on structure-intensive tasks such as path planning. Reasoning schemes further shape how stored spatial knowledge is used, with advanced prompts supporting more effective multi-step inference. We further observe that spatial reasoning performance saturates across model versions and scales beyond a certain capability threshold, indicating that improvements in map-based spatial understanding require mechanisms tailored to spatial representation and reasoning rather than scaling alone. --- ### Can Small Training Runs Reliably Guide Data Curation? Rethinking Proxy-Model Practice Authors: Jiachen T. Wang, Tong Wu, Kaifeng Lyu, James Zou, Dawn Song, Ruoxi Jia, Prateek Mittal Published: 2025-12-30 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.24503v2 Data teams at frontier AI companies routinely train small proxy models to make critical decisions about pretraining data recipes for full-scale training runs. However, the community has a limited understanding of whether and when conclusions drawn from small-scale experiments reliably transfer to full-scale model training. In this work, we uncover a subtle yet critical issue in the standard experimental protocol for data recipe assessment: the use of identical small-scale model training configurations across all data recipes in the name of "fair" comparison. We show that the experiment conclusions about data quality can flip with even minor adjustments to training hyperparameters, as the optimal training configuration is inherently data-dependent. Moreover, this fixed-configuration protocol diverges from full-scale model development pipelines, where hyperparameter optimization is a standard step. Consequently, we posit that the objective of data recipe assessment should be to identify the recipe that yields the best performance under data-specific tuning. To mitigate the high cost of hyperparameter tuning, we introduce a simple patch to the evaluation protocol: using reduced learning rates for proxy model training. We show that this approach yields relative performance that strongly correlates with that of fully tuned large-scale LLM pretraining runs. Theoretically, we prove that for random-feature models, this approach preserves the ordering of datasets according to their optimal achievable loss. Empirically, we validate this approach across 23 data recipes covering four critical dimensions of data curation, demonstrating dramatic improvements in the reliability of small-scale experiments. ---